Engram is a retrieval system of meaning, saving both HBM storage and bandwidth
teortaxesTex · x · 2026-09-22
Thread on DeepSeek's Engram: bookwormengr explains Engram/N-gram is not a computational system but a retrieval system of meaning (embeddings); its real benefit is not just 40-50% HBM storage savings but HBM bandwidth, which is even more expensive. teortaxesTx notes everyone wants to expand sparse memory to 80% of parametric volume, which seems hard with such impoverished but performant representations.
Related event: DeepSeek Engram Is Semantic Retrieval, Can Cut HBM Needs 40-50%(4 posts)→
More from Infra
- California signs seven bills making AI data centers pay their own utility costs — The Verge AI · 2026-09-22
- O'Reilly builds a working data vocabulary for the semantic era, from warehouses to ontologies — rseroter · 2026-09-22
- UK's most powerful government AI supercomputer cost £225m — same as one bridge — emax · 2026-09-22
- exe.dev wins over developers: SSH into root VMs, plus the underrated Shelley coding agent — davidcrawshaw · 2026-09-22
- NVIDIA hosts trilateral meeting as Artificial Analysis becomes Korea sovereign AI evaluator — ArtificialAnlys · 2026-09-22
- Lisa Su's Generational Run: AMD Market Cap Up 300x to $1T, Data Center CPU Share Hits 40%+ — xiaosun86 · 2026-09-22